Create a Powerful RAG Chatbot in 10 Minutes with IBM watsonx | No Coding | IBM Business Partners
HTML-код
- Опубликовано: 13 сен 2024
- This video demonstrates how to easily create a RAG chatbot using IBM watsonx Assistant, watson Discovery, and watsonx.ai. Learn about the typical RAG process and how to set up watson Discovery, watsonx.ai, and watsonx Assistant. Feel free to reach out with any questions!
[Updated Aug 16 2024]: please name your extension as "watson ai" and "watson discovery" for the action to capture the parameters of the extension.
If you are facing the errors of “Invoke watsonx generation api” or "search", check the extension config and make sure you provide the parameters for the extension. Here are two examples for your reference:
watsonx ai extension parameter config: github.com/lan...
watson discovery extension parameter config: github.com/lan...
[Files used in the video]
IBM Annual report 2022: www.ibm.com/in...
watsonx ai openapi:
The file used in the video: github.com/lan...
IBM Github repo: github.com/wat...
watson discovery openapi:
The file used in the video: github.com/lan...
IBM Github repo: github.com/wat...
watson assistant RAG actions:
github.com/lan...
The following action is the base version I used to build above action, where I modified the response from watson discovery and reference part at each response.
github.com/wat...
@IBM @IBMTechnology @SMtv2022e @techdata7709 #ai #generativeai #watsonx
Thank you very much, it helped me a lot.
Glad it helped!
Thanks, what a great demo! Very helpful
My pleasure!
This is fantastic. Good Job
Thank you very much!
how users can provision resources w/o the techzone?
After you sign up IBM cloud, there will be free tier/trials for the service mentioned in the video.
Hi, the watsonx ai openapi file you are using in the demo is different and the one in the description is different. Hence a lot of people are facing errors with “Invoke watsonx generation api”. The link you have provided is the default file available on ibm documentation and it does not go with your custom actions file. Can you share the watsonx ai openapi json file you used in the demo please?
Thanks for the info! Just uploaded.
@@shenglan-channel is it the screenshot? or is it a file. The link would be highly appreciated🙏
Hi @ShahilNikhailJagjivan, please check the video descriptions, it has the links to the file on github repo. Thanks
Hi Sheng, thanks for the great sharing! it seems the JSON of watson assistant RAG actions doesn't work now, may I learn is there any version change during these two months?
Hi Li Chun, please try this action json file: github.com/lansheng919/watsonx-RAG-Demo-action
which I used in the video. Feel free to reach out if any questions (sheng.lan@techdata.com). Thanks.
@@shenglan-channel the url is not working
Thanks @shenglan-channel for the video.@@mubeenarasack3625 the link works, remove the final ), unfortunately it also doesn't let me load the .json file in watson assistant like
@lichun00868, it generates "Internal Error"
Hi @Cammediname, thanks for your comment, I add more details in the video description, which maybe helpful for you to troubleshot. Thanks
Hi, I´m having the same problem. Did you find the way to solve it?
Very Nice👍
Thank you! Cheers!
Thank you very much for this wonderful introduction on how to set up the chat bot! I still have a question about the capabilities. I want to use a chat bot to ask customers specific questions and have the responses analzed and stored in a standardised way in a data base. For Instance: The chat bot asks for the satisfaction and then analyzes the response to give it a numerical value from 1 to 5. Is it generally possible to use watsonx in such a way? How do I develop such a tool? Any help would be much appreciated!
Thanks for your kind words!
Yes, watsonx assistant is capable for this more structured conversation. Check how to build action in watsonx assistant should help and get you start to build the chatbot, here is the link:cloud.ibm.com/docs/watson-assistant?topic=watson-assistant-build-actions-overview
Let me know if any more questions, thanks!
@@shenglan-channel awesome, thank you very much, I really appreciate it!
Hi Sheng, I have followed the same instructions but unfortunately I see missing extension error for "Invoke watsonx generation API" .. is there anything needs to be fixed. However other 2 are fine. please advice
Thanks for your questions, maybe try to inspect your extension to get more information to debug. Here is a link to give your more information how to do it,
cloud.ibm.com/docs/watson-assistant?topic=watson-assistant-call-extension#extension-debug
AI that answers questions sometimes still hallucinates; is there a way to address this issue? And also how you can get the "for more context on this answer please see" info in the assistant?
Thank you very much
Great questions, one of the main purpose of RAG is to reduce hallucination by providing context. But still, I haven't seen a solution to remove hallucination 100%. Most of approaches I have seen are to "beg" LLM not to answer if the context is not relevant in RAG solution and always check the response.
For more context part is via Watson Assistant (WA), you can manipulate the context variables in WA and display it in the response. I can share you the action Json for more details, feel free to email me (sheng.lan@techdata.com), Thanks!
Can i hopedully use this on the Free plan?
Yes, I think the watsonx assistant has a free tier, and watson discovery has free trial.
The web crawl for the 2022 pdf takes a very long time, cant we just upload the pdf?
Yes, upload pdf is another option!
What’s chatbot provider is better botpress voice flow or ibm?
IBM